---
title: "Genai Conversation Spans"
method: POST
path: "/agents/conversations/spans"
tags: ["Agents"]
---

# Genai Conversation Spans

`POST /agents/conversations/spans`

## Request body

- AgentConversationSpansReq — Request the span sequences for an explicit set of conversations. Reads span scalar columns only (no message bodies) for the given `conversation_ids`. Powers the conversations-list spans minimap.
  - `project_id` string, required
  - `conversation_ids` string[]
  - `started_after` string, date-time, nullable
  - `started_before` string, date-time, nullable

## Response `200`

Successful Response

- AgentConversationSpansRes — Span sequences + feedback markers, one entry per requested conversation.
  - `conversations` AgentConversationSpans[]
    - `conversation_id` string, required
    - `spans` AgentConversationSpan[]
      - `operation_name` string, required
      - `trace_id` string, required
      - `span_id` string, required
      - `status` 'UNSET' | 'OK' | 'ERROR', required
      - `duration_ms` integer, required
    - `spans_feedback` AgentConversationSpanFeedback[]
      - `trace_id` string, nullable, required — The turn this feedback is anchored to; None for conversation-level.
      - `feedback_type` 'wandb.agent_user_feedback' | 'wandb.agent_monitor', required
      - `tags` string[] — Arbitrary descriptive tags applied to this feedback.
      - `ratings` AgentConversationSpanRating[] — Numeric scorer ratings applied to this feedback.
        - `name` string, required
        - `value` number, required
        - `reason` string, nullable
        - `confidence` number, nullable

## Other responses

- `422` — Validation Error

---

[API](https://skmtc.net/wandb/apis/serverless-training.md) · [All operations](https://skmtc.net/wandb/apis/serverless-training/llms.txt) · [OpenAPI document](https://skmtc-service-staging.skmtc.workers.dev/v1/apis/wandb/serverless-training/revisions/8d8d96fc0fd3/schema)